Assistance creating/training a Neural Network on R

I need someone who is proficient at using R to produce and train neural networks to check/redo my work.

I am a Neural Network/R newbie, who is attempting to train a neural network with 15 inputs and 1 output using the AMORE library. I am using a dataset that has 16 columns (15 columns for inputs and 1 for outputs) and 124 rows (1 row per unit).

Thus far, my interpretation has been that I don't need to distinguish a training set from testing set for the function to work. Instead, I have created subsets from my dataset, and then vectors from those subsets, in order to provide the 'inputs' and 'targets' for the function. However, I am not sure that I have interpreted this correctly.

The function runs without error but I remain suspicious.

This is what I wrote:

mydata mydata[1:124,2]
P = as.vector(input,mode = 'numeric')
TARGET = as.vector(output,mode = 'numeric')

library(AMORE)

#Feedforward network with 1 hidden layer
net<-newff(n.neurons = c(15,4,1),
learning.rate.global = 0.01,
momentum.global = 0.9,
error.criterium = "LMS",
Stao=NA, hidden.layer="sigmoid",
output.layer = "sigmoid",
method = "ADAPTgdwm")

result<- train(net,P,TARGET, error.criterium = "LMS",report = TRUE,
n.shows = 15,show.step = 200)

y<-sim(result$net,TARGET)
plot(mydata[,1],y,col='blue', pch='+')
points(P,TARGET,col='red',pch='x')